Stars
ScalarLM - a unified training and inference stack
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
A fancy self-hosted monitoring tool
speech to text benchmark framework
Open source audio recorder and transcriber for MacOS
Third party firmware for Asus routers (newer codebase)
Benchmarking Intelligence Efficiency of LM Inference
Post-training with Tinker
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Containerization is a Swift package for running Linux containers on macOS.
Voice Activity Detector (VAD) : low-latency, high-performance and lightweight
🍺 The missing package manager for macOS (or Linux)
The official repo for paper "Spatial Speech Translation: Translating Across Space With Binaural Hearables"
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Fully open reproduction of DeepSeek-R1
The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
Docker First Application example. Created for "A beginner’s guide to Docker — how to create your first Docker application" article on HereWeCode.
A step by step guide to fine-tuning the DeepSeek R1 Distilled models on Apple Silicon machines.
Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection
Ubuntu for Rockchip RK35XX Devices
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Labs for the EE292D Edge ML class at Stanford